© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59269
    Prev
    Next
    INDEX
    Explanations

    blood vessels

    np_acts-logits-general · gemini-2.5-flash-lite

    methods, structures, and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    코
    0.46
     Everglades
    0.44
    dy
    0.43
    ваются
    0.42
    TH
    0.41
    K
    0.40
    এস
    0.40
    (!
    0.40
     从
    0.40
    レイン
    0.40
    POSITIVE LOGITS
     att
    0.51
     methodologies
    0.48
     justifications
    0.43
     methodology
    0.43
     servants
    0.41
     objek
    0.40
     prox
    0.40
     صرف
    0.39
     justific
    0.39
     méthod
    0.39
    Activations Density 0.000%

    No Known Activations